On Thu, Sep 18, 2008 at 7:16 PM, Gorka Guardiola <[EMAIL PROTECTED]> wrote:
> A real pity none of you are coming :-(.
>
it's a bad time of year: Supercomputing is around this time. It was
just a bit more travel than most of us could pull off.
Have a good time. I still want to come visit your lab
On Fri, Sep 19, 2008 at 1:15 AM, ron minnich <[EMAIL PROTECTED]> wrote:
> This was going into greece but I am not going and they aren't either so:
> /n/sources/contrib/rminnich/tracepaper/trace.ps
>
> The modified 8l described in the paper is also in that directory. If
> you want the trace dev let
This was going into greece but I am not going and they aren't either so:
/n/sources/contrib/rminnich/tracepaper/trace.ps
The modified 8l described in the paper is also in that directory. If
you want the trace dev let me know.
Code was aki, ron, and john.
Comments are welcome.
Thanks
ron
I think I made it using a user-level program to talk to 9p
servers trying to do some caching. I'll try to find out if I still
have it in venti,
I think I just removed
the thing after finding out it was not going to work for retrieving omero trees.
On Thu, Sep 18, 2008 at 10:05 PM, Steve Simon <[EM
> We did this, IIRC. It helped reduce latency, but...
Are the modified kernel files still in your venti?
I would be interested in having a play in a simple disk file
sharing environment.
-Steve
> I'm not saying I know it would be a good idea, but you could implement
> speculative-9P which issued the equivalent of the batched requests
> without waiting for the responses of the prior request -- since you
> are on an in-order pipe the file server would get the requests in
> order and if they
> I was using a 3c589 until a few years ago, then I moved to
> a Netgear FA411 which is somwhat more mechanically robust -
> I broke the plug on the 3com card :-(
It sounds like for a number of people it's working just
fine, and no one's put forward any real magic to make
it work, except for usin
> There's is some code laying around for Broadcom 570x cards:
> http://plan9.bell-labs.com/sources/contrib/uriel/mirror/bc.tgz
I'll take a look at it. I seem to recall some discussion of
it and that it was in a pretty incomplete state. If I'm
remembering correctly, I'm thinking my chances might
On Thu, Sep 18, 2008 at 8:34 AM, sqweek <[EMAIL PROTECTED]> wrote:
> On Thu, Sep 18, 2008 at 7:51 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
>
> How can multiple threads possibly help with latency caused by
> operations that forced to be serial by the protocol? In fact, how can
> multithreading
On Thu, Sep 18, 2008 at 7:51 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
>> Hm, but what's the alternative here? Readahead seems somewhat
>> attractive, if difficult (I worry about blocking reads and timing
>> sensitive file systems).
>
> the fundamental problem is that it becomes very difficult
On Thu, Sep 18, 2008 at 6:51 AM, erik quanstrom <[EMAIL PROTECTED]> wrote:
>> On Fri, Sep 12, 2008 at 7:47 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
>> also...
>
> the fundamental problem is that it becomes very difficult to
> implement fileservers which don't serve up regular files.
> you migh
> On Fri, Sep 12, 2008 at 7:47 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
> > as an aside: i don't think 9p itself limits plan 9 performance
> > over high-latency links. the limitations have more to do with
> > the number of outstanding messages, which is 1 in the mnt
> > driver.
>
> Hm, but
> I see that ndb/dnsquery returns correct information on my system, but
> I noticed that there is not a default domainname, like on linux, in /
> etc/resolv.conf we set the "search domainname" ... is there a similar
> setting in plan9
plan 9 dns tries to look up unrooted (no ".") names in the loca
See dnsdomain attribute in ndb(6).
Yarek.
2008/9/18 <[EMAIL PROTECTED]>:
> I see that ndb/dnsquery returns correct information on my system, but
> I noticed that there is not a default domainname, like on linux, in /
> etc/resolv.conf we set the "search domainname" ... is there a similar
> setti
Actually, this whole subject was thoroughly discussed at the *first*
iwp9; but apparently nobody is bothered by this enough to implement
any of the then suggested solutions.
Op is not one the solutions discussed at the time, and saying 'just
use another protocol' is not a way to resolve the shortc
* sqweek <[EMAIL PROTECTED]> [080918 12:02]:
> On Fri, Sep 12, 2008 at 7:47 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
> > as an aside: i don't think 9p itself limits plan 9 performance
> > over high-latency links. the limitations have more to do with
> > the number of outstanding messages, whi
On Fri, Sep 12, 2008 at 7:47 PM, erik quanstrom <[EMAIL PROTECTED]> wrote:
> as an aside: i don't think 9p itself limits plan 9 performance
> over high-latency links. the limitations have more to do with
> the number of outstanding messages, which is 1 in the mnt
> driver.
Hm, but what's the alt
I see that ndb/dnsquery returns correct information on my system, but
I noticed that there is not a default domainname, like on linux, in /
etc/resolv.conf we set the "search domainname" ... is there a similar
setting in plan9
18 matches
Mail list logo
